Rohan Paul

@rohanpaul_ai

A 9B model beating a frontier flagship 4x on biomedical extraction is something. @OvermindLab launched a platform that turns a company's own agent data into small specialist models the company owns. It records what an agent does in production, turns those records into training data, then fine-tunes and serves an open-weight model. Customers can download the weights, retrain them or roll back, and the platform code is open source under AGPL-3.0. check out the below charts for its performance data. e.g. in one case across more than 4K questions on more than 100 contracts, Overmind's tuned 9B model found the right clause with 91.6% F1 against GPT-5.6 Luna's 82.0%.
打开原帖#511482
  1. Research

    François Chollet: The critical distinction between base LLMs (2024 and earlier) and mod…
  2. Industry

    Michael Truell: Grok Bot gets useful work done, without you needing to ask.
  3. Industry

    Aravind Srinivas: We're open-sourcing our multimodal Decision model and offering it thr…